Avi Kivity wrote: > On 06/23/2009 02:44 PM, Michael S. Tsirkin wrote: >> On Tue, Jun 23, 2009 at 12:04:06AM -0400, Gregory Haskins wrote: >> >>>>> It will also need to support >>>>> multiple matches. >>>>> >>>>> >>>> What, signal many fds on the same address/value pair? >>>> I see this as a bug. Why is this a good thing to support? >>>> Just increases the chance of leaking this fd. >>>> >>>> >>> I believe Avi asked for this feature specifically, so I will defer >>> to him. >>> >> >> Hmm. That's hard to implement in my model. Avi, can we give up >> this feature? I don't think anyone needs this specifically ... >> > > I think we can make do with passing that single eventfd to multiple > consumers. It means their event count reads may return zero, but I > guess we can live with that. > > I do want to retain flexibility in how we route events. > Ok, so for now I will just crank up the io_bus array, and we can address scale another day. Can I just drop patch 2/3 and let the io_bus govern the limit? -Greg
Attachment:
signature.asc
Description: OpenPGP digital signature
